Difficulties In Classification Research Articles

Gene Based Disease Prediction using Pattern Similarity Based Classification

In today’s biology research in a single experiment scientist can simultaneously measure the expression of levels of thousands of genes. The molecular level of the cell is represented in gene expression profile. And it helps for medical diagnosis tools. For addressing the fundamental harms which helps to diagnosis and discovery gene expression data along with diseases classification is included. Monitoring of large number of gene expressions is possible because of this DNAmicroarray technique. Using this large quantity of gene data, experts are trying to find the probability of disease classification using gene expression dataset. Number of technique has been formed with comfortable results over these years. Still there are issues which need to be address and understood. To overcome this disease classification difficulty, it is required to review at the problem, the related issues and proposed solutions together. This paper presents a comprehensive clustering method and classification method such as Partial Swarm Optimization algorithm, K-NN classification algorithm and estimate them based on theirclassification accuracy,evaluation time and to reveal biological information about genes. Based on our multiclass classification method to diagnosis the diseases and also find severity levels of diseases. Our experimental results show that proposed semi supervised classifier performance improved in accuracy percentage.

SNR analysis with speckle noise in interferometry using monochromatic expanded source and fringe localization

As a strongly coherent light source, laser is widely used in various high-precision interferometry techniques. However, the coherence of laser also produces coherence noise. Laser coherence noise degrades the signal-to-noise (SNR) ratio and the interferogram resolution, leading to difficulties in data classification and information restoration. Here, we aim to derive the expressions of laser speckle contrast and SNR of interferograms through the theory of laser speckle noise. The factors affecting the speckle contrast and SNR of images are analyzed theoretically. The problem of fringe localization caused by dynamic scatter is discussed. We verify the relevant expression by using an experimental system and find that it can serve as a basis of laser interferometry to analyze measurement accuracy and suppress speckle noise.

Phenetic analysis of Curcuma spp. in Yogyakarta, Indonesia based on morphological and anatomical characters

Abstract. Sungkawati M, Hidayati L, Daryono BS, Purnomo. 2019. Phenetic analysis of Curcuma spp. in Yogyakarta, Indonesia based on morphological and anatomical characters. Biodiversitas 20: 2340-2347. Curcuma spp., also known as ginger (Zingiberaceae), has economic value in traditional medicine. However, its many morphological variations cause difficulties in identification and classification. Therefore, observation of its morphological and anatomical characteristics, and of the phenetic relationships between Curcuma species, is important. This research aims to determine the specific characteristics of Curcuma spp. and to examine its phenetic relationships based on morphological and anatomical characteristics. The research was conducted in July 2018-February 2019 in the Bantul, Gunungkidul, Sleman and Karanganyar regions. Observation of the anatomical characteristics was conducted on the leaves and rhizomes and the data analyzed according to descriptive and quantitative/numerical methods. Clustering analysis with the Gower General Similarity Coefficient and Principal Component Analysis (PCA) was performed to determine the role of each character in groupings. The results of the research found seven species from 23 OTUs observed (C. aeruginosa, C. domestica, C. manga and C. xanthorrhiza, each with four OTUs; C. soloensis and C. zedoaria, with three OTUs each; and C. heyneana with one OTU) and showed that specific morphological characteristics were found in the flesh color rhizome, pseudostem color and midrib color. Specific anatomical characteristics were evident in the secretion cell color and the presence of trichomes on the leaves and rhizomes. The dendrogram shows a 0.70 phenon line consisting of two groups, group A (C. soloensis and C. domestica) fused in a 0.760 similarity index, and group B (C. aeruginosa, C. mangga, C. heyneana, C. soloensis, C. xanthorrhiza and C. zedoaria) fused in a 0.654 similarity index, which means that C. soloensis and C. domestica have a close phenetic relationship. The 0.80 phenon line consisted of five groups: C. domestica, C. soloensis, C. xanthorrhiza, C. zedoaria-C. mangga-C. heyneana and C. aeruginosa.

Progressive Cascaded Convolutional Neural Networks for Single Tree Detection with Google Earth Imagery

High-resolution remote sensing images can not only help forestry administrative departments achieve high-precision forest resource surveys, wood yield estimations and forest mapping but also provide decision-making support for urban greening projects. Many scholars have studied ways to detect single trees from remote sensing images and proposed many detection methods. However, the existing single tree detection methods have many errors of commission and omission in complex scenes, close values on the digital data of the image for background and trees, unclear canopy contour and abnormal shape caused by illumination shadows. To solve these problems, this paper presents progressive cascaded convolutional neural networks for single tree detection with Google Earth imagery and adopts three progressive classification branches to train and detect tree samples with different classification difficulties. In this method, the feature extraction modules of three CNN networks are progressively cascaded, and the network layer in the branches determined whether to filter the samples and feed back to the feature extraction module to improve the precision of single tree detection. In addition, the mechanism of two-phase training is used to improve the efficiency of model training. To verify the validity and practicability of our method, three forest plots located in Hangzhou City, China, Phang Nga Province, Thailand and Florida, USA were selected as test areas, and the tree detection results of different methods, including the region-growing, template-matching, convolutional neural network and our progressive cascaded convolutional neural network, are presented. The results indicate that our method has the best detection performance. Our method not only has higher precision and recall but also has good robustness to forest scenes with different complexity levels. The F1 measure analysis in the three plots was 81.0%, which is improved by 14.5%, 18.9% and 5.0%, respectively, compared with other existing methods.

Metagenomic Classification using Centrifuge

To assess the quality of food is a major challenge the food industry faces today. It is of utmost importance to test it for contaminates and non-edible material that may be present. To overcome these challenges metagenomic classification is majorly useful. Several researches involve various classification techniques and their studies. Difficulties in metagenomic classification include increasing number of genomes thereby requirement of computational methods to have high speed as well as high accuracy so as to compare DNA sequences to genomes. Centrifuge is a classification tool for quantification of species present in a sample so as to monitor the quality of the same. Given a food sample Centrifuge effectively classifies the species present in it enabling a timely and accurate analysis.

CircDeep: deep learning approach for circular RNA classification from other long non-coding RNA.

MotivationOver the past two decades, a circular form of RNA (circular RNA), produced through alternative splicing, has become the focus of scientific studies due to its major role as a microRNA (miRNA) activity modulator and its association with various diseases including cancer. Therefore, the detection of circular RNAs is vital to understanding their biogenesis and purpose. Prediction of circular RNA can be achieved in three steps: distinguishing non-coding RNAs from protein coding gene transcripts, separating short and long non-coding RNAs and predicting circular RNAs from other long non-coding RNAs (lncRNAs). However, the available tools are less than 80 percent accurate for distinguishing circular RNAs from other lncRNAs due to difficulty of classification. Therefore, the availability of a more accurate and fast machine learning method for the identification of circular RNAs, which considers the specific features of circular RNA, is essential to the development of systematic annotation.ResultsHere we present an End-to-End deep learning framework, circDeep, to classify circular RNA from other lncRNA. circDeep fuses an RCM descriptor, ACNN-BLSTM sequence descriptor and a conservation descriptor into high level abstraction descriptors, where the shared representations across different modalities are integrated. The experiments show that circDeep is not only faster than existing tools but also performs at an unprecedented level of accuracy by achieving a 12 percent increase in accuracy over the other tools.Availability and implementation https://github.com/UofLBioinformatics/circDeep.Supplementary information Supplementary data are available at Bioinformatics online.

Abstract Concepts Through the Lens of Linguistic and Extra-Linguistic Knowledge

The paper deals with the rigorous methods used in the research of concepts representing abstract notions like “friendship”, “love”, “hatred”, “conscience”, and “envy”. Concepts of that kind have no visible physical support in the material world except for the sound forms of the words representing them, thus causing additional difficulties in classification, research and analysis as well as stipulating the use of both linguistic and extra-linguistic methods in the process. The language provides access to a concept nominating only its certain part, which may not be the most significant. The study points out the importance of subjective cognition and empiric experience of a person in the process of verbalisation of abstract entities. The cognitive approach, in which certain phenomena are found, allows us to include in the framework of study essential as well as complex linguistic and extra-linguistic knowledge about it, despite the degree to which they are presented in the language. It’s essential to set out the necessity to take into account the social and cultural background of an individual. The authors pay particular attention to the ambiguity and inevitable subjectivity in the study of abstract concepts, due to their formation scheme complexity and vagueness. The combination of linguistic and extra-linguistic procedures allows us to give the fullest and deepest analysis of the investigated event, because in the structure of abstract concepts and in the simultaneous presence of an invariant core there are a huge range of personal associations.

Research on Musical Sentiment Classification Model Based on Joint Representation Structure

In the traditional music emotion classification process, there are problems such as low classification accuracy rate, long period, and difficulty in satisfying the individualized needs of the theme music in people’s lives. Based on this, a neural network model based on joint representation structure is designed. The model uses low-level descriptors and spectrograms to construct a joint representation of the characteristics of the manual and convolutional recurrent neural network, thus realizing the discrimination of music emotion subclasses. At the time of the experiment, the model was designed and the CRNN traditional model was used as the baseline. The experimental results show that this model can improve the classification accuracy of music emotions compared with the traditional single model.

A Multi-Feature Fusion Based on Transfer Learning for Chicken Embryo Eggs Classification

The fertility detection of Specific Pathogen Free (SPF) chicken embryo eggs in vaccine preparation is a challenging task due to the high similarity among six kinds of hatching embryos (weak, hemolytic, crack, infected, infertile, and fertile). This paper firstly analyzes two classification difficulties of feature similarity with subtle variations on six kinds of five- to seven-day embryos, and proposes a novel multi-feature fusion based on Deep Convolutional Neural Network (DCNN) architecture in a small dataset. To avoid overfitting, data augmentation is employed to generate enough training images after the Region of Interest (ROI) of original images are cropped. Then, all the augmented ROI images are fed into pretrained AlexNet and GoogLeNet to learn the discriminative deep features by transfer learning, respectively. After the local features of Speeded Up Robust Feature (SURF) and Histogram of Oriented Gradient (HOG) are extracted, the multi-feature fusion with deep features and local features is implemented. Finally, the Support Vector Machine (SVM) is trained with the fused features. The verified experiments show that this proposed method achieves an average classification accuracy rate of 98.4%, and that the proposed transfer learning has superior generalization and better classification performance for small-scale agricultural image samples.

Revision and morphological analysis of the Ragadidae (Insecta, Diptera)

Several taxonomic groups within Empidoidea Latreille, 1809 have been subject to unclear phylogenetic assignments along with multiple parallel hypotheses causing difficulties in classification and morphological identification. This study reviews the internal classification of the Ragadidae and includes a diagnosis and description of all included subfamilies and genera based on the results of an analysis of morphological characters using maximum parsimony. Illustration of important characters and a key to all genera in the family is given. The genus Hormopeza Zetterstedt, 1838 is found to be most closely related to Anthepiscopus Becker, 1891 and Iteaphila Zetterstedt, 1838, and the subfamily Iteaphilinae Wahlberg & Johanson, 2018 is therefore expanded to also include that genus. Hormopeza is consequently excluded from Ragadinae Sinclair, 2016. This study provides diagnoses, descriptions and keys in a contribution to a thorough classification of the empidoid groups and increased ease in morphological recognition.

DNA BARCODING APPLICATION OF MITOCHONDRIAL COI GENE TO IDENTIFY SOME FISH SPECIES OF FAMILY GOBIIDAE IN VIETNAM

The family Gobiidae is a relatively high abundance family of coastal fish with about 2000 species in 210 genera described. In Vietnam, the study on Gobiidae is very complex due to the large number of species, small size and high morphological variation which makes difficulties in identification and classification. In this study, the DNA barcoding technique has been used through mitochondrial cytochrome oxidase I (COI) gene to classify 30 specimens of Gobiidae from three coastal areas (North, Central and South) in Vietnam to evaluate the effectiveness compared to the morphological classification method. Results showed that 26 species belonging to 21 genera were determined by the COI barcode while 19 species (17 genera) were determined when using morphological method. Mahidolia mystacina was new recorded in Vietnam. The DNA barcodes of COI gene developed in this study could be useful for estimating phylogenetic diversity as well as other studies of gobiids in terms of conservation, management and utilization of fisheries resources in Vietnam. In addition, the results showed the high potentiality in using COI barcode to identify marine fish.

Multi-label biomedical question classification for lexical answer type prediction.

Question classification is considered one of the most significant phases of a typical Question Answering (QA) system. It assigns certain answer types to each question which leads to narrow down the search space of possible answers for factoid and list type questions. The process of assigning certain answer types to each question is also known as Lexical Answer Type (LAT) Prediction. Although much work has been done to enhance the performance of question classification into coarse and fine classes in diverse domains, it is still considered a challenging task in the biomedical field. The difficulty in biomedical question classification stems from the fact that one question might have more than one label or expected answer types associated with it (also, referred to as a multi-label classification). In the biomedical domain, only preliminary work is done to classify multi-label questions by transforming them into a single label through copy transformation technique. In this paper, we have generated a multi-labeled corpus (MLBioMedLAT) by exploring the process of Open Advancement of Question Answering (OAQA) system for the task of biomedical question classification. We use 780 biomedical questions from BioASQ challenge and assign them appropriate labels. To annotate these labels, we use the answers for each question and assign the question semantic type labels by leveraging an existing corpus and utilizing OAQA system. The paper introduces a data transformation approach namely Label Power Set with logistic regression (LPLR) for the task of multi-label biomedical question classification and compares its performance with Structured SVM (SSVM), Restricted Boltzmann Machine (RBM), and copy transformation based logistic regression (CLR) (previously used for a similar task in the OAQA system). To evaluate the integrity of the introduced data transformation technique, we use three prominent evaluation measures namely MicroF1, Accuracy, and Hamming Loss. Regarding MicroF1, our introduced technique coupled with a new feature set surpasses CLR, SSVM, and RBM with a margin of 7%, 8%, and 22% respectively.

ASSESSMENT OF MOLECULAR BIOMARKERS FOR BLADDER CANCER DIAGNOSIS, GRADING AND PROGNOSIS

Worldwide, bladder cancer is a very significant public health problem, in terms of prevalence, mortality and management for individuals and their families. Bladder cancer is the fourth most commonly diagnosed cancer in men and one of the heaviest cancers in terms of cost. Although transurethral resection of the bladder followed by intravesical instillation of live attenuated Bacillus Calmette–Guerin (BCG) is considered as the gold standard for patients with intermediate and high risk, only a small portion of patient responds to the BCG-therapy. Bladder cancer management is faced by the therapy failure, great side effects and some difficulties in histological classification. Accordingly, growing interest is given to the use of genetic, epigenetic and immunologic biomarkers for molecular signature characterization and tumor stratification. In Morocco, great efforts have been made to contribute to the improvement of management of bladder cancer and many studies were made to evaluate some genetic and epigenetic biomarkers. Generated data is of a great interest for characterization of bladder cancer tumors in Morocco and could be used for better management of this disease.

Intertidal area classification with generalized extreme value distribution and Markov random field in quad-polarimetric synthetic aperture radar imagery

Classification of intertidal area in synthetic aperture radar (SAR) images is an important yet challenging issue when considering the complicatedly and dramatically changing features of tidal fluctuation. The difficulty of intertidal area classification is compounded because a high proportion of this area is frequently flooded by water, making statistical modeling methods with spatial contextual information often ineffective. Because polarimetric entropy and anisotropy play significant roles in characterizing intertidal areas, in this paper we propose a novel unsupervised contextual classification algorithm. The key point of the method is to combine the generalized extreme value (GEV) statistical model of the polarization features and the Markov random field (MRF) for contextual smoothing. A goodness-of-fit test is added to determine the significance of the components of the statistical model. The final classification results are obtained by effectively combining the results of polarimetric entropy and anisotropy. Experimental results of the polarimetric data obtained by the Chinese Gaofen-3 SAR satellite demonstrate the feasibility and superiority of the proposed classification algorithm.

Review of short-text classification

PurposeRapid developments in social networks and their usage in everyday life have caused an explosion in the amount of short electronic documents. Thus, the need to classify this type of document based on their content has a significant implication in many applications. The need to classify these documents in relevant classes according to their text contents should be interested in many practical reasons. Short-text classification is an essential step in many applications, such as spam filtering, sentiment analysis, Twitter personalization, customer review and many other applications related to social networks. Reviews on short text and its application are limited. Thus, this paper aims to discuss the characteristics of short text, its challenges and difficulties in classification. The paper attempt to introduce all stages in principle classification, the technique used in each stage and the possible development trend in each stage.Design/methodology/approachThe paper as a review of the main aspect of short-text classification. The paper is structured based on the classification task stage.FindingsThis paper discusses related issues and approaches to these problems. Further research could be conducted to address the challenges in short texts and avoid poor accuracy in classification. Problems in low performance can be solved by using optimized solutions, such as genetic algorithms that are powerful in enhancing the quality of selected features. Soft computing solution has a fuzzy logic that makes short-text problems a promising area of research.Originality/valueUsing a powerful short-text classification method significantly affects many applications in terms of efficiency enhancement. Current solutions still have low performance, implying the need for improvement. This paper discusses related issues and approaches to these problems.

Phylogenetic inference in section Archerythroxylum informs taxonomy, biogeography, and the domestication of coca (Erythroxylum species).

This investigation establishes the first DNA-sequence-based phylogenetic hypothesis of species relationships in the coca family (Erythroxylaceae) and presents its implications for the intrageneric taxonomy and neotropical biogeography of Erythroxylum. We also identify the closest wild relatives and evolutionary relationships of the cultivated coca taxa. We focused our phylogenomic inference on the largest taxonomic section in the genus Erythroxylum (Archerythroxylum O.E.Schulz) using concatenation and gene tree reconciliation methods from hybridization-based target capture of 427 genes. We show that neotropical Erythroxylum are monophyletic within the paleotropical lineages, yet Archerythroxylum and all of the other taxonomic sections from which we sampled multiple species lack monophyly. We mapped phytogeographic states onto the tree and found some concordance between these regions and clades. The wild species E. gracilipes and E. cataractarum are most closely related to the cultivated E. coca and E. novogranatense, but relationships within this "coca" clade remain equivocal. Our results point to the difficulty of morphology-based intrageneric classification in this clade and highlight the importance of integrative taxonomy in future systematic revisions. We can confidently identify E. gracilipes and E. cataractarum as the closest wild relatives of the coca taxa, but understanding the domestication history of this crop will require more thorough phylogeographic analysis.

Fine classification of ultra-low permeability reservoirs around the Placanticline of Daqing oilfield (PR of China)

Under SY/T 6285-2011 classification standard in China, reservoirs of which permeability ranging from 1 × 10−3μm2 to 10 × 10−3μm2 are divided into ultra-low permeability reservoir. While development practice of ultra-low permeability reservoirs around the Placanticline of Daqing shows that, water-breakthrough time and development effect of different reservoir types are greatly different. Besides the permeability values, reservoir fracture development is another important factor affecting development effect of ultra-low permeability reservoirs. Therefore, based on geologic characteristics of 63 blocks in ultra-low permeability reservoirs around the Placanticline of Daqing oilfield, using fracture parameters as primary classification index, matrix permeability, average throat radius, pore-throat ratio, movable fluid saturation and fluid mobility as main classification indexes, the method combined with grey correlation analysis, multi-parameter cluster analysis, dynamic-static consistency check and comprehensive evaluation is established. The classification evaluation criteria for two groups and four sub-groups has been determined, and the classification results of each block are verified. The results show that this method solves the problem of classification difficulty caused by classification parameters of individual blocks falling in different classification areas and realizes the goal of rational classification of 63 developed ultra-low permeability blocks. At the same time, it has the characteristics of simple calculation and high accuracy, which provides a powerful basis for the efficient and fine classification of ultra-low permeability blocks with similar geological characteristics.

Diversity and Evolution of Living Oysters

ABSTRACT Oysters are difficult to classify because of plasticity in shell morphology. Difficulties in classification have hindered the understanding of oyster diversity and evolution. Recent molecular studies of living oysters have revealed high genetic diversity at species, population, and genome levels. New and cryptic species have been discovered, revealing surprisingly high species diversity under similar shell morphology. Genetic analyses have identified several species complexes where low genetic divergence indicates recent or ongoing speciation during the past 3–4 million years. Ongoing speciation is also supported by exceptionally high population divergence within some species. The oyster genome is highly polymorphic and gene-rich, with extensive expansion of genes related to stress and immune responses. High levels of genetic diversity and gene expansion in oysters are likely adaptations to variable environments. Local adaptation in oysters may be pervasive but countered by strong gene flow and b...

An analysis of 3D knee kinematic data complexity in knee osteoarthritis and asymptomatic controls.

Three-dimensional (3D) knee kinematic data, measuring flexion/extension, abduction/adduction, and internal/external rotation angle variations during locomotion, provide essential information to diagnose, classify, and treat musculoskeletal knee pathologies. However, and so across genders, the curse of dimensionality, intra-class high variability, and inter-class proximity make this data usually difficult to interpret, particularly in tasks such as knee pathology classification. The purpose of this study is to use data complexity analysis to get some insight into this difficulty. Using 3D knee kinematic measurements recorded from osteoarthritis and asymptomatic subjects, we evaluated both single feature complexity, where each feature is taken individually, and global feature complexity, where features are considered simultaneously. These evaluations afford a characterization of data complexity independent of the used classifier and, therefore, provide information as to the level of classification performance one can expect. Comparative results, using reference databases, reveal that knee kinematic data are highly complex, and thus foretell the difficulty of knee pathology classification.

WHO/ISUP classification, grading and pathological staging of renal cell carcinoma: standards and controversies

PurposePathological parameters assessed on biopsies and resection specimens have a pivotal role in the diagnosis, prognosis and management of patients with renal cell carcinoma (RCC).MethodsA non-systematic literature search was performed, updated to January 2018, to identify key standards and controversies in the pathological classification, grading and staging of RCC.ResultsAlthough most RCCs exhibit characteristic morphology that enables easy categorisation, RCCs show considerable morphological heterogeneity and it is not uncommon for there to be difficulty in assigning a tumour type, especially with rarer tumour subtypes. The differentiation between benign and malignant oncocytic tumours remains a particular challenge. The development of additional immunohistochemical and molecular tests is needed to facilitate tumour typing, because of the prognostic and therapeutic implications, and to enable more reliable identification of poorly differentiated metastatic tumours as being of renal origin. Any new tests need to be applicable to small biopsy samples, to overcome the heterogeneity of renal tumours. There is also a need to facilitate identification of tumour types that have genetic implications, to allow referral and management at specialist centres. Digital pathology has a potential role in such referral practice.ConclusionMuch has been done to standardise pathological assessment of renal cell carcinomas in recent years, but there still remain areas of difficulty in classification and grading of these heterogeneous tumours.